WO2022227489A1

WO2022227489A1 - Collision detection method and apparatus for objects, and device and storage medium

Info

Publication number: WO2022227489A1
Application number: PCT/CN2021/130014
Authority: WO
Inventors: 曲达
Original assignee: 北京百度网讯科技有限公司
Priority date: 2021-04-26
Filing date: 2021-11-11
Publication date: 2022-11-03
Also published as: CN113077548A; CN113077548B

Abstract

A collision detection method and apparatus for objects, and a device and a storage medium, applied to the technical field of electronics, and in particular to the technical field of intelligent traffic and map navigation. The specific implementation scheme of the collision detection method for the objects comprises: obtaining attribute information of each of two objects to be detected (S210), the attribute information comprising rotation positions of said objects relative to a predetermined three-dimensional space and size information of said objects projected to a predetermined two-dimensional plane; determining the size information of a bounding box of each of said objects on the basis of the size information of each of said objects in the said two objects (S230), the bounding box taking the rotation position of each of said objects as a center; and determining a collision result of said two objects according to the rotation positions of said two objects and the size information of the bounding boxes of said two objects (S250).

Description

Collision detection method, device, device and storage medium for objects

This application claims the priority of Chinese Patent Application No. 202110456769.4 filed on April 26, 2021, the contents of which are incorporated herein by reference.

technical field

The present disclosure relates to the field of electronic technology, in particular to the technical field of intelligent transportation and map navigation, and more particularly to a method, device, device and storage medium for collision detection for objects.

Background technique

With the development of electronic technology, panoramic technology has emerged. Panorama technology is a new visual technology, which can bring users a new real sense of presence and interactive experience.

When setting up a panorama display, the panorama 2D image is usually mapped in the created 3D ball model to create a 3D scene. After the 3D scene is created, markers and label information are usually added to the 3D ball model to provide guidance information to the user.

SUMMARY OF THE INVENTION

Provided are a collision detection method, device, electronic device and storage medium for objects that improve detection accuracy.

According to one aspect of the present disclosure, there is provided a collision detection method for objects, including: acquiring attribute information of two objects to be detected, the attribute information including the rotational position of the objects to be detected relative to a predetermined three-dimensional space and the objects to be detected. The size information projected to a predetermined two-dimensional plane; based on the size information of each to-be-detected object in the two to-be-detected objects, determine the size information of the bounding box of each to-be-detected object, and the bounding box takes the rotation position of the to-be-detected object as and determining the collision result of the two objects to be detected according to the rotational positions of the two objects to be detected and the size information of the bounding boxes of the two objects to be detected.

According to another aspect of the present disclosure, a collision detection device for objects is provided, comprising: an information acquisition module configured to acquire respective attribute information of two objects to be detected, where the attribute information includes the relative relationship between the objects to be detected relative to a predetermined three-dimensional space The rotational position of the object to be detected and the size information of the object to be detected projected to the predetermined two-dimensional plane; the size information determination module is used to determine the size of the bounding box of each object to be detected based on the size information of each of the two objects to be detected. size information, the bounding box is centered on the rotational position of the object to be detected; and a collision result determination module for determining two to-be-detected objects according to the rotational position of the two to-be-detected objects and the size information of the bounding boxes of the two to-be-detected objects Detect collision results of objects.

According to another aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor. The at least one processor executes, so that the at least one processor can execute the collision detection method for an object provided by the present disclosure.

According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the collision detection method for an object provided by the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, which, when executed by a processor, implements the collision detection method for an object provided by the present disclosure.

It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present disclosure. in:

1 is a schematic diagram of an application scenario of a collision detection method, apparatus, electronic device, and storage medium for objects according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of a method for collision detection for an object according to an embodiment of the present disclosure;

3 is a schematic diagram of the principle of determining a mapping relationship between a predetermined two-dimensional plane and a predetermined three-dimensional space according to an embodiment of the present disclosure;

4 is a schematic diagram of the principle of determining the size information of the bounding box of each object to be detected according to an embodiment of the present disclosure;

5 is a schematic diagram of the principle of determining a collision result of two objects to be detected according to an embodiment of the present disclosure;

6 is a schematic diagram of a principle of determining a collision result of two objects to be detected according to another embodiment of the present disclosure;

FIG. 7 is a structural block diagram of a collision detection apparatus for an object according to an embodiment of the present disclosure; and

FIG. 8 is a block diagram of an electronic device used to implement the collision detection method for an object according to an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

The present disclosure provides a collision detection method for an object, which includes an information acquisition stage, a size information determination stage, and a collision result determination stage. In the information acquisition stage, the respective attribute information of the two objects to be detected is acquired, the attribute information includes the rotational position of the object to be detected relative to the predetermined three-dimensional space and the size information of the object to be detected projected onto the predetermined two-dimensional plane. In the size information determination stage, the size information of the bounding box of each object to be detected is determined based on the size information of each of the two objects to be detected, and the bounding box is centered on the rotational position of the object to be detected. In the collision result determination stage, the collision result of the two objects to be detected is determined according to the rotational positions of the two objects to be detected and the size information of the bounding boxes of the two objects to be detected.

The application scenarios of the method and apparatus provided by the present disclosure will be described below with reference to FIG. 1 .

FIG. 1 is a schematic diagram of an application scenario of a collision detection method, apparatus, electronic device, and storage medium for objects according to an embodiment of the present disclosure.

As shown in FIG. 1 , the application scenario 100 includes a server 110 and a terminal device 130 . The terminal device 130 may be communicatively connected to the server 110 through a network, and the network may include a wired or wireless communication link.

For example, the user may use the terminal device 130 to interact with the server 110 through the network to receive or send messages and the like. The terminal device 130 may be a terminal device having a display screen with a panorama display function, including but not limited to a smart watch, a smart phone, a tablet computer, a laptop computer, and the like.

For example, the terminal device 130 may be installed with various client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, social platform software or map navigation applications (just examples).

The server 110 may be a server that provides various services, such as a background management server that provides support for client applications installed on the terminal device 130 . The server can be a cloud server, a distributed system server, or a server combined with blockchain.

Exemplarily, the terminal device 130 may, for example, send a request for obtaining panoramic scene information to the server 110 in response to a user operation. For example, the server 110 may send the panorama model 120 to the terminal device 130 in response to the acquisition request, where the panorama model 120 includes the panorama image and tag information added to the objects in the panorama image, and the like. After receiving the panorama model 120, the terminal device 130 may render the panorama scene in the running client application, and display the tag information added to the object near the displayed object. For example, for a train station in the displayed panoramic scene, a label 131 indicating "train station" may be displayed, and for a convenience store in the displayed panoramic scene, a label 132 indicating "convenience store" may be displayed.

According to an embodiment of the present disclosure, as shown in FIG. 1 , the application scenario may further include a database 140 . The database 140 stores a plurality of images that can be stitched into a panoramic image, or stores a panoramic image. The server 110 may, for example, access the database 140 and build a panoramic model from the images obtained from the database 140 . Specifically, you can create a 3D ball model first, map the acquired image in the 3D ball model, and add labels to each object. At the same time, if there are many objects in the predetermined area, the server may also perform collision detection on multiple tags of multiple objects in the predetermined area, and determine the display rules of the multiple tags according to the collision detection results. The display rule may also be carried in the panoramic model 120 constructed by the server 110, so that the terminal device can render and display the label of the object.

It should be noted that the collision detection method for objects provided by the present disclosure may be executed by the server 110 . Correspondingly, the collision detection device for objects provided by the present disclosure may be provided in the server 110 . The collision detection method for objects provided by the present disclosure may also be performed by a server or server cluster that is different from the server 110 and can communicate with the server 110 . Correspondingly, the collision detection device for objects provided by the present disclosure may also be provided in a server or a server cluster that is different from the server 110 and can communicate with the server 110 .

It should be understood that the number and type of servers, terminal devices and databases in FIG. 1 are merely illustrative. There can be any number and type of servers, terminal devices and databases according to implementation needs.

FIG. 2 is a flowchart of a collision detection method for an object according to an embodiment of the present disclosure.

As shown in FIG. 2 , the collision detection method 200 for an object in this embodiment may include operation S210 , operation S230 and operation S250 .

In operation S210, respective attribute information of the two objects to be detected is acquired.

According to an embodiment of the present disclosure, the attribute information may include a rotational position of the object to be detected relative to a predetermined three-dimensional space. The predetermined three-dimensional space may be a 3D ball model created based on a 3D drawing protocol. Specifically, the 3D ball model can be constructed by calling a JavaScript Web Graphics Library (Web Graphics Library, WebGL). The rotation position may be the position of the center point of the object to be detected relative to the center point of the 3D ball model. The predetermined three-dimensional space is a three-dimensional space formed by the 3D ball model. It can be understood that, the above-mentioned construction method of the 3D ball model is only used as an example to facilitate understanding of the present disclosure, which is not limited in the present disclosure.

Exemplarily, the rotational position may be determined according to the azimuth angle value, the pitch angle value and the distance of the center point of the object to be detected relative to the center point of the 3D ball model.

Exemplarily, considering that two objects in the 3D spherical model that are located in the same azimuth and do not overlap, although the distance from the center point is not equal, since the azimuth angle value and the pitch angle value are the same, they are projected to a predetermined two-dimensional When the planes are overlapped, the collision detection result of the two objects is collision. Therefore, in this embodiment, collision detection can be performed only on objects located in different azimuths, that is, two objects with different azimuth angle values and/or different pitch angle values can be regarded as objects to be detected. Whether or not the two objects to be detected will overlap when projected on a predetermined two-dimensional plane mainly depends on the azimuth angle value and the pitch angle value of the object to be detected. Therefore, the rotational position of this embodiment may only include the azimuth angle value and the pitch angle value of the center point of the object to be detected relative to the center point of the predetermined three-dimensional space.

According to an embodiment of the present disclosure, the attribute information may further include size information of the object to be detected projected onto a predetermined two-dimensional plane. The size information may include, for example, the display height and display width of the object to be detected in a predetermined two-dimensional plane. The predetermined two-dimensional plane may be the plane where the display screen of the terminal device is located, and the terminal device is used for displaying a panoramic picture.

According to an embodiment of the present disclosure, the object to be detected may be an object in a panoramic scene, or may be a tag added to an object in the panoramic scene.

In operation S230, size information of the bounding box of each object to be detected is determined based on the size information of each of the two objects to be detected.

According to the embodiments of the present disclosure, the size information of the object to be detected in the predetermined two-dimensional plane can be converted into the size information in the predetermined three-dimensional space according to the mapping relationship between the predetermined three-dimensional space and the predetermined two-dimensional plane. Taking the rotation position of the object to be detected as the center, and according to the converted size information in the predetermined three-dimensional space, a bounding box when the object to be detected is mapped to the predetermined three-dimensional space is constructed.

Exemplarily, when the bounding box is projected onto a predetermined two-dimensional plane, the projected shape may be, for example, a rectangle, a circle, or an ellipse. The above structure of the bounding box is only used as an example to facilitate understanding of the present disclosure, which is not limited in the present disclosure.

Exemplarily, in the related art, when the object to be detected is a label added to an object in a panoramic scene, the location information of the bounding box is usually determined according to the positioning coordinates of the label relative to the upper left corner of the viewport and a predetermined size, That is, the bounding box is constructed based on a two-dimensional plane. In this way, when the display area in the panoramic scene changes, the position of the center point of the bounding box will change. Furthermore, since the center point of the bounding box is represented by the positioning coordinates of the bounding box relative to the upper left corner of the viewport, when the distance between the bounding box and the upper left corner of the viewport is farther, the calculation error of the positioning coordinates will be higher. . In order to solve this problem, the related art usually performs real-time collision detection on the labels of objects in the current field of view when switching the display area, so as to improve the detection accuracy, but this will undoubtedly result in high computational overhead, and the rendering efficiency of the display area after switching is low. The problem.

In the embodiment of the present disclosure, the size information of the bounding box in the predetermined three-dimensional space is obtained by converting based on the size information of the object to be detected in the predetermined two-dimensional plane, and the rotation position of the object to be detected is used as the center to construct the bounding box in the three-dimensional space. The location information of the bounding box is not affected by changes in the field of view. Therefore, it is convenient to perform collision detection on tags in advance before rendering the entire panoramic scene. Compared with the technical solutions of related technologies that require real-time detection, the calculation overhead can be reduced to a certain extent, and the rendering efficiency of the pictures in the panoramic scene can be improved. Therefore, it is convenient for users to improve experience.

In operation S250, a collision result of the two objects to be detected is determined according to the rotational positions of the two objects to be detected and the size information of the bounding boxes of the two objects to be detected.

According to an embodiment of the present disclosure, it can be determined whether two bounding boxes overlap according to the distance between the center points of the two bounding boxes and the size information of the two bounding boxes. If the two bounding boxes overlap, it can be determined that the collision result of the two objects to be detected is a collision. If the two bounding boxes do not overlap, it can be determined that the collision result of the two objects to be detected is non-collision.

Exemplarily, since the rotation position of the object to be detected is taken as the center point of the bounding box, the distance between the center points of the two bounding boxes is the distance between the two rotation positions. In this embodiment, the distance between the two rotation positions can be compared with the size of the space that can be enclosed by the two bounding boxes when the two bounding boxes fit together. The distance between the center points, you can determine that the two bounding boxes overlap.

To sum up, in this embodiment, by taking the center point of the object to be detected in the predetermined three-dimensional space as the center of the central bounding box and constructing the bounding box in the three-dimensional space, the accuracy of the determined position information of the bounding box can be improved. Therefore, collision detection can be performed on all objects to be detected at one time when the panoramic scene is initialized, which can save computational overhead and improve the accuracy of collision detection.

FIG. 3 is a schematic diagram of the principle of determining a mapping relationship between a predetermined two-dimensional plane and a predetermined three-dimensional space according to an embodiment of the present disclosure.

According to the embodiments of the present disclosure, when determining the size information of the bounding box, the mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional plane may be determined first. Based on the mapping relationship and the size information of the object to be detected projected onto the predetermined two-dimensional plane, the size information of the bounding box in the three-dimensional space is obtained by conversion.

Exemplarily, the mapping relationship may, for example, represent a relationship between a unit length in a predetermined two-dimensional plane and a rotation angle in a predetermined three-dimensional space. When determining the mapping relationship, the viewing angle value of the center point of the predetermined three-dimensional space in the predetermined direction with respect to the predetermined two-dimensional plane and the width of the predetermined two-dimensional plane in the predetermined direction may be obtained. The ratio of the viewing angle value to the width is used as the mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional plane.

Exemplarily, as shown in FIG. 3 , the embodiment 300 can obtain the viewing angle value a required for viewing the entire predetermined two-dimensional plane 320 in the width direction starting from the center point O of the predetermined three-dimensional space 310, or viewing in the height direction. The viewing angle value β required for the entire predetermined two-dimensional plane 320 . In one embodiment, the viewing angle value of the center point of the predetermined three-dimensional space in the predetermined direction with respect to the predetermined two-dimensional plane is: in the camera projection matrix determined according to the predetermined three-dimensional space and the predetermined two-dimensional plane, the field of view in the horizontal direction ( Field of View, FOV) value or vertical field of view value. When the aforementioned predetermined direction is the horizontal direction, the obtained viewing angle value is a. When the aforementioned predetermined direction is the vertical direction, the obtained viewing angle value is β.

Exemplarily, as shown in FIG. 3 , the embodiment 300 can acquire the width a or the height b of a predetermined two-dimensional plane. In one embodiment, the width a and height b are the width and height of the display screen of the terminal device. When the aforementioned predetermined direction is the horizontal direction, the obtained width is a. When the aforementioned predetermined direction is the vertical direction, the obtained width is b. Therefore, the mapping relationship M=a/a or M=β/b between the predetermined two-dimensional plane and the predetermined three-dimensional space can be determined.

Through the determination of the mapping relationship, it is convenient to convert the size information of the object to be detected on the predetermined two-dimensional plane into the size information of the object to be detected in the predetermined three-dimensional space, thereby facilitating the construction of a bounding box of the object to be detected.

FIG. 4 is a schematic diagram of the principle of determining the size information of the bounding box of each object to be detected according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the rotational position of the object to be detected relative to the predetermined three-dimensional space may include a first rotation angle of the center point of the object to be detected relative to the first coordinate axis in the spherical coordinate system constructed based on the predetermined three-dimensional space and a second rotation angle relative to the second coordinate axis. The first rotation angle and the second rotation angle are perpendicular to each other.

Exemplarily, in the embodiment 400 shown in FIG. 4 , a spherical coordinate system can be established by taking the center point O of the 3D spherical model 410 as the coordinate origin. If the center point of the object to be detected is point p on the spherical surface, the rotation position of the object to be detected relative to the predetermined three-dimensional space includes: the rotation angle of point p relative to the X axis

The rotation angle λ of point p relative to the Y axis. Wherein, the rotation angle of point p relative to the X axis and the rotation angle relative to the Y axis can be determined according to the right-hand rotation rule. Specifically, the pointing direction of the thumb is perpendicular to the bending direction of the four fingers, the pointing direction of the thumb is the positive direction of the rotation axis, and the bending direction of the four fingers is the positive rotation direction to determine the rotation angle relative to the rotation axis.

According to an embodiment of the present disclosure, the present disclosure can also locate the rotation position according to the azimuth angle value and the pitch angle value of the center point of the object to be detected in the constructed spherical coordinate system, for example.

According to the embodiments of the present disclosure, after the mapping relationship is determined, the conversion between the size information of the object to be detected projected to the predetermined two-dimensional plane and the size information of the object to be detected in the predetermined three-dimensional space can be realized. The display form of the object to be detected in the predetermined two-dimensional space is usually in the form of a rectangular frame 420, and the size information of the object to be detected projected onto the predetermined two-dimensional plane may include the width of the object to be detected and the height of the object to be detected. For example, in the embodiment 400 shown in FIG. 4 , the size information projected to a predetermined two-dimensional plane includes a width c 431 and a height d 432 . The center point p of the object to be detected is projected onto a predetermined two-dimensional plane corresponding to point p'.

According to an embodiment of the present disclosure, the first size information of the bounding box of each object to be detected can be determined according to the width and mapping relationship of each object to be detected. For example, the first size information may represent half of the azimuth size of the bounding box in the spherical coordinate system constructed based on the predetermined three-dimensional space, that is, when the width is mapped to the predetermined three-dimensional space, the center point of the object to be detected is taken as the origin, in the horizontal direction The upper limit of the absolute value of the rotation angle. The second size information of the bounding box of each object to be detected may be determined according to the height and mapping relationship of each object to be detected. The second size information may, for example, represent the pitch size of the bounding box in the spherical coordinate system constructed based on the predetermined three-dimensional space, that is, when the height is mapped to the predetermined three-dimensional space, the center point of the object to be detected is taken as the origin, allowing rotation in the pitch direction The upper limit of the absolute value of the angle.

Exemplarily, as shown in FIG. 4 , according to the width c 431 of the object to be detected and the mapping relationship M 440 determined above, it can be determined that the azimuth size of the bounding box in the spherical coordinate system constructed based on the predetermined three-dimensional space is c*M, Then the first size information 451 can be expressed as W=0.5*c*M. According to the height d 432 of the object to be detected and the mapping relationship M 440 determined above, it can be obtained that the pitch size of the bounding box in the spherical coordinate system constructed based on the predetermined three-dimensional space is d*M, then the second size information 452 can be expressed as H =0.5*d*M.

Exemplarily, when the bounding box of the object to be detected is rectangular in the predetermined two-dimensional plane, the first size information 451 and the second size information 452 determined above are the size information of the bounding box, and the object to be detected is in the predetermined three-dimensional space. The coordinate value of the rotation position of , and the size information together constitute the bounding box information. By setting the bounding box that is rectangular on the predetermined two-dimensional plane, the bounding box can completely surround the object to be detected, and at the same time, the size of the bounding box can be reduced as much as possible. Misjudgment of the collision result.

Exemplarily, when the bounding box of the object to be detected is a circle in a predetermined two-dimensional plane, after the first size information 451 and the second size information 452 are determined, for example, the first size information 451 and the second size information 451 may also be determined. The larger value in the two size information 452 is used as the size information of the bounding box of the object to be detected, so as to ensure that the bounding box can completely surround the object to be detected. Specifically, it can be determined that the size information of the bounding box of the object to be detected is R=max(H, W).

FIG. 5 is a schematic diagram of the principle of determining a collision result of two objects to be detected according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, as shown in FIG. 5 , when the shape obtained by projecting the bounding box onto a predetermined two-dimensional plane is a rectangle, the embodiment 500 projects two bounding boxes of two objects to be detected onto a predetermined two-dimensional plane. Plane, for example, rectangle 510 and rectangle 520 can be obtained. In order that the two objects to be detected do not overlap when projected onto the predetermined two-dimensional plane, it is required that the rectangle 510 and the rectangle 520 do not overlap. That is, the rectangle 510 and the rectangle 520 need to meet the following conditions: the half width w ₁ of the rectangle 510 and the half width w ₂ of the rectangle 520 are less than or equal to the distance between the point p ₁ ' and the point p ₂ ' in the width direction, half of the rectangle 510 The height h ₁ and the half height h ₂ of the rectangle 520 are less than or equal to the distance between the point p ₁ ' and the point p ₂ ' in the height direction. Wherein, p ₁ ' is the center point of the projection of one of the two objects to be detected on the predetermined two-dimensional plane (that is, the center point of the bounding box of the one of the objects to be detected projected to the predetermined two-dimensional plane), p ₂ ' is the center point of the projection of the other object to be detected on the predetermined two-dimensional plane (that is, the center point of the projection of the bounding box of the other object to be detected to the predetermined two-dimensional plane). By mapping this condition to a predetermined three-dimensional space according to the mapping relationship, the following conditions can be obtained:

(W ₁ +W ₂ )≤diffλ, where diffλ=|λ ₁ −λ ₂ |;

in,

Wherein, W ₁ is the first size information of the bounding box of one of the objects to be detected, and H ₁ is the second size information of the bounding box of one of the objects to be detected. W ₂ is the first size information of the bounding box of the other object to be detected, and H ₂ is the second size information of the bounding box of the other object to be detected. λ ₁ is the first rotation angle of one of the objects to be detected, that is, the rotation angle relative to the Y axis described above,

is the second rotation angle of one of the objects to be detected, that is, the rotation angle relative to the X-axis described above. λ ₂ is the first rotation angle of the other object to be detected, that is, the rotation angle relative to the Y-axis described above,

is the second rotation angle of the other object to be detected, that is, the rotation angle relative to the X-axis described above.

In this embodiment, when determining the collision result of the two objects to be detected, the first difference value diffλ between the two first rotation angles of the two objects to be detected can be determined first, and the two first rotation angles of the two objects to be detected can be determined. The second difference between the two rotation angles

Based on the size of the bounding box determined above, determine the sum of the first size information of the two bounding boxes of the two objects to be detected, so as to obtain the first size sum (W ₁ +W ₂ ), and determine the size of the two objects to be detected. The sum of the second size information of the two bounding boxes to obtain the second size sum (H ₁ +H ₂ ). According to the magnitude relationship between the first difference diffλ and the first size sum (W ₁ +W ₂ ), and the second difference

The size relationship between the second size and (H ₁ +H ₂ ) determines the collision result of the two objects to be detected. If the first size sum (W ₁ +W ₂ ) is greater than the first difference diffλ, or the second size sum (H ₁ +H ₂ ) is greater than the second difference

Then it is determined that the collision result is a collision; otherwise, it can be determined that the collision result is a non-collision.

FIG. 6 is a schematic diagram of a principle of determining a collision result of two objects to be detected according to another embodiment of the present disclosure.

According to an embodiment of the present disclosure, as shown in FIG. 6 , when the shape obtained by projecting the bounding box onto a predetermined two-dimensional plane is a circle, the embodiment 600 projects two bounding boxes of two objects to be detected onto a predetermined two-dimensional plane. Dimension plane, for example, circle 610 and circle 620 can be obtained. In order to make the two objects to be detected do not overlap when projected onto the predetermined two-dimensional plane, it is required that the circle 610 and the circle 620 do not overlap. That is, the circle 610 and the circle 620 need to satisfy the following conditions: the radius r ₁ of the circle 610 and the radius r ₂ of the circle 620 are less than or equal to the distance between the point p ₁ ′ and the point p ₂ ′. Wherein, p ₁ ' is the center point of the projection of one of the two objects to be detected on the predetermined two-dimensional plane (that is, the center point of the bounding box of the one of the objects to be detected projected to the predetermined two-dimensional plane), p ₂ ' is the center point of the projection of the other object to be detected on the predetermined two-dimensional plane (that is, the center point of the projection of the bounding box of the other object to be detected to the predetermined two-dimensional plane). By mapping this condition to a predetermined three-dimensional space according to the mapping relationship, the following conditions can be obtained:

where diffλ=|λ ₁ -λ ₂ |,

Among them, R ₁ is the size information of the bounding box of one of the objects to be detected. R ₂ is the size information of the bounding box of the other object to be detected, λ ₁ is the first rotation angle of one of the objects to be detected, that is, the rotation angle relative to the Y axis described above,

Based on the size of the bounding box determined above, the sum of the size information of the two bounding boxes of the two objects to be detected is determined, and the size sum (R ₁ +R ₂ ) is obtained. According to the first difference diffλ and the second difference

arithmetic square root of

The size relationship between the size and (R ₁ +R ₂ ) determines the collision result of the two objects to be detected. If the sum of dimensions (R ₁ +R ₂ ) is greater than the arithmetic square root

In a panorama scene of map navigation, the tag added to the entity in the panorama screen can be used as the object to be detected, and the collision detection method for objects described above can be used to perform collision detection on any two objects to be detected. In this way, among all the added tags, the tags that will overlap each other when the panorama is displayed. For two tags that overlap each other, for example, a tag with a higher weight value may be selected from the two tags for display according to the pre-assigned weight value for the two tags. In this way, the overall visual experience in the current field of view in the panoramic scene of map navigation can be optimized, and thus the user experience can be improved. It can be understood that the pre-allocated weight value can be set according to actual needs, for example, it can be set according to the click frequency. The higher the click frequency, the larger the pre-allocated weight value.

It can be understood that the above tags are used as examples of objects to be detected only to facilitate understanding of the present disclosure, and the collision detection method for objects provided in the present disclosure can be applied to any scene requiring collision detection.

Based on the above-mentioned collision detection method for objects, the present disclosure further provides a collision detection device for objects, which will be described in detail below with reference to FIG. 7 .

FIG. 7 is a structural block diagram of a collision detection apparatus for an object according to an embodiment of the present disclosure.

As shown in FIG. 7 , the collision detection apparatus 700 for objects in this embodiment may include an information acquisition module 710 , a size information determination module 730 and a collision result determination module 750 .

The information acquisition module 710 is configured to acquire respective attribute information of the two objects to be detected, the attribute information includes the rotational position of the objects to be detected relative to a predetermined three-dimensional space and size information of the objects to be detected projected onto a predetermined two-dimensional plane. In an embodiment, the information acquisition module 710 may be configured to perform, for example, the operation S210 described above, which will not be repeated here.

The size information determination module 730 is configured to determine size information of a bounding box of each object to be detected based on the size information of each of the two objects to be detected, the bounding box being centered on the rotational position of the object to be detected. In an embodiment, the size information determination module 730 may be configured to perform, for example, the operation S230 described above, which will not be repeated here.

The collision result determination module 750 is configured to determine the collision result of the two objects to be detected according to the rotational positions of the two objects to be detected and the size information of the bounding boxes of the two objects to be detected. In an embodiment, the collision result determination module 750 may be configured to perform, for example, the operation S250 described above, which will not be repeated here.

According to an embodiment of the present disclosure, the size information determination module 730 may include, for example, a mapping relationship determination submodule and a size information determination submodule. The mapping relationship determination submodule is used to determine the mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional space. The size information determination submodule is configured to determine the size information of the bounding box of each object to be detected based on the mapping relationship and the size information of each object to be detected.

According to an embodiment of the present disclosure, the above-mentioned mapping relationship determination submodule includes a viewing angle value acquisition unit, a width acquisition unit, and a relationship determination unit. The viewing angle value acquiring unit is used for acquiring the viewing angle value of the center point of the predetermined three-dimensional space in the predetermined direction with respect to the predetermined two-dimensional plane. The width acquiring unit is used for acquiring the width of the predetermined two-dimensional plane in the predetermined direction. The relationship determining unit is configured to determine the mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional space as the ratio of the viewing angle value to the width.

According to an embodiment of the present disclosure, the above-mentioned rotational position of the object to be detected relative to the three-dimensional space includes: a center point of the object to be detected is in a spherical coordinate system constructed based on a predetermined three-dimensional space, and a first rotation with the first coordinate axis as the rotation axis angle; and a second rotation angle of the center point of the object to be detected in a spherical coordinate system constructed based on a predetermined three-dimensional space, with the second coordinate axis as the rotation axis. Wherein, the first coordinate axis and the second coordinate axis are perpendicular to each other.

According to an embodiment of the present disclosure, the size information of the object to be detected projected onto the predetermined two-dimensional plane includes the width of the object to be detected and the height of the object to be detected. The size information determination submodule may include, for example, an azimuth size determination unit and an elevation size determination unit. The azimuth size determining unit is used to determine the first size information of the bounding box of each object to be detected according to the width and mapping relationship of each object to be detected, the first size information including the spherical coordinates of the bounding box constructed based on the predetermined three-dimensional space half of the azimuth dimension in the system. The pitch size determination unit is used to determine the second size information of the bounding box of each object to be detected according to the height of each object to be detected and the mapping relationship, the second size information includes the spherical coordinates of the bounding box constructed based on the predetermined three-dimensional space Half the pitch size in the system.

According to an embodiment of the present disclosure, the aforementioned collision result determination module may include, for example, a first difference determination submodule, a first size and determination submodule, and a first collision determination submodule. The first difference determination submodule is used to determine the first difference between the two first rotation angles of the two objects to be detected, and to determine the second difference between the two second rotation angles of the two objects to be detected value. The first size sum determination submodule is used to determine the sum of the first size information of the two bounding boxes of the two objects to be detected, and obtain the first size sum; and is used to determine the second size of the two bounding boxes of the two objects to be detected. The sum of the size information, the second size sum is obtained. The first collision determination submodule is configured to determine the collision result of the two objects to be detected based on the size relationship between the first difference value and the first size sum and the size relationship between the second difference value and the second size sum.

According to an embodiment of the present disclosure, the size information determination submodule further includes a size information determination unit for determining the larger value of the first size information and the second size information as size information of the bounding box of each object to be detected.

According to an embodiment of the present disclosure, the above-mentioned collision result determination module includes a second difference determination submodule, a second size and determination submodule, and a second collision determination submodule. The second difference determination submodule is used to determine the first difference between the two first rotation angles of the two objects to be detected, and to determine the second difference between the two second rotation angles of the two objects to be detected difference. The second size sum determination submodule is used to determine the sum of the size information of the two bounding boxes of the two objects to be detected, and obtain the size sum. The second collision determination sub-module is configured to determine the collision result of the two objects to be detected based on the magnitude relationship between the first difference value and the arithmetic square root of the second difference value and the size sum.

In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved are all in compliance with relevant laws and regulations, and do not violate public order and good customs.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

8 shows a schematic block diagram of an example electronic device 800 that may be used to implement the method of collision detection for objects of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 8 , the device 800 includes a computing unit 801 that can be executed according to a computer program stored in a read only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803 Various appropriate actions and handling. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input/output (I/O) interface 805 is also connected to bus 804 .

Various components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc. ; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 809 allows the device 800 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Computing unit 801 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 801 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as collision detection methods for objects. For example, in some embodiments, a collision detection method for an object may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 808 . In some embodiments, part or all of the computer program may be loaded and/or installed on device 800 via ROM 802 and/or communication unit 809. When a computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of the collision detection method for an object described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform a collision detection method for an object by any other suitable means (eg, by means of firmware).

Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a distributed system server, or a server combined with blockchain.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders. As long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, there is no limitation herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure should be included within the protection scope of the present disclosure.

Claims

A collision detection method for objects, comprising:

Acquiring respective attribute information of the two objects to be detected, the attribute information includes the rotational position of the object to be detected relative to a predetermined three-dimensional space and size information of the object to be detected projected onto a predetermined two-dimensional plane;

Based on the size information of each of the two objects to be detected, the size information of the bounding box of each of the objects to be detected is determined, and the bounding box is centered on the rotational position of the object to be detected ;as well as

According to the rotational positions of the two objects to be detected and the size information of the bounding boxes of the two objects to be detected, a collision result of the two objects to be detected is determined.
The method according to claim 1, wherein determining the size information of the bounding box of each of the objects to be detected comprises:

determining a mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional space; and

Based on the mapping relationship and size information of each of the objects to be detected, the size information of the bounding box of each of the objects to be detected is determined.
The method according to claim 2, wherein the determining the mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional space comprises:

acquiring a viewing angle value of the center point of the predetermined three-dimensional space in a predetermined direction with respect to the predetermined two-dimensional plane;

obtaining the width of the predetermined two-dimensional plane in the predetermined direction; and

The mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional space is determined as the ratio of the viewing angle value to the width.
The method according to claim 2 or 3, wherein the rotational position of the object to be detected relative to the three-dimensional space comprises:

The center point of the object to be detected is in the spherical coordinate system constructed based on the predetermined three-dimensional space, and the first coordinate axis is the first rotation angle of the rotation axis; and

The center point of the object to be detected is in the spherical coordinate system constructed based on the predetermined three-dimensional space, and the second coordinate axis is the second rotation angle of the rotation axis,

Wherein, the first coordinate axis and the second coordinate axis are perpendicular to each other.
The method according to claim 4, wherein the size information of the object to be detected projected to the predetermined two-dimensional plane includes the width of the object to be detected and the height of the object to be detected; The size information of the bounding box of the object to be detected includes:

According to the width of each object to be detected and the mapping relationship, first size information of the bounding box of each object to be detected is determined, and the first size information includes the bounding box based on the predetermined three-dimensional half of the azimuth dimension in the spatially constructed spherical coordinate system; and

According to the height of each object to be detected and the mapping relationship, second size information of the bounding box of each object to be detected is determined, and the second size information includes the bounding box based on the predetermined three-dimensional Half of the pitch dimension in the spatially constructed spherical coordinate system.
The method according to claim 5, wherein determining the collision result of the two objects to be detected comprises:

determining a first difference between two first rotation angles of the two objects to be detected, and determining a second difference between two second rotation angles of the two objects to be detected;

Determine the sum of the first size information of the two bounding boxes of the two objects to be detected, and obtain the first size sum; and determine the sum of the second size information of the two bounding boxes of the two objects to be detected, and obtain the second dimension and; and

Based on the size relationship between the first difference value and the first size sum and the size relationship between the second difference value and the second size sum, determine the collision result of the two objects to be detected .
The method according to claim 5, wherein determining the size information of the bounding box of each of the objects to be detected further comprises:

A larger value of the first size information and the second size information is determined as the size information of the bounding box of each of the objects to be detected.
The method according to claim 7, wherein determining the collision result of the two objects to be detected comprises:

determining a first difference between two first rotation angles of the two objects to be detected, and determining a second difference between two second rotation angles of the two objects to be detected;

Determine the sum of the size information of the two bounding boxes of the two objects to be detected, and obtain the size sum; and

Based on the magnitude relationship between the arithmetic square root of the first difference value and the second difference value and the size sum, a collision result of the two objects to be detected is determined.
A collision detection device for objects, comprising:

The information acquisition module is used to acquire the respective attribute information of the two objects to be detected, the attribute information includes the rotational position of the object to be detected relative to the predetermined three-dimensional space and the size information of the object to be detected projected to the predetermined two-dimensional plane ;

A size information determination module, configured to determine size information of a bounding box of each of the objects to be detected based on the size information of each of the two objects to be detected, the bounding box being the size of the object to be detected The rotational position of the detected object is centered; and

The collision result determination module is configured to determine the collision result of the two objects to be detected according to the rotational positions of the two objects to be detected and the size information of the bounding boxes of the two objects to be detected.
The apparatus of claim 9, wherein the size information determination module comprises:

a mapping relationship determination submodule, configured to determine a mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional space; and

The size information determination submodule is configured to determine the size information of the bounding box of each of the objects to be detected based on the mapping relationship and the size information of each of the objects to be detected.
The apparatus according to claim 10, wherein the mapping relationship determination submodule comprises:

a viewing angle value obtaining unit, configured to obtain a viewing angle value of the center point of the predetermined three-dimensional space in a predetermined direction with respect to the predetermined two-dimensional plane;

a width acquiring unit, configured to acquire the width of the predetermined two-dimensional plane in the predetermined direction; and

A relationship determination unit, configured to determine the mapping relationship between the predetermined two-dimensional plane and the predetermined three-dimensional space as the ratio of the viewing angle value to the width.
The device according to claim 10 or 11, wherein the rotational position of the object to be detected relative to the three-dimensional space comprises:

The center point of the object to be detected is in the spherical coordinate system constructed based on the predetermined three-dimensional space, and the first coordinate axis is the first rotation angle of the rotation axis; and

The center point of the object to be detected is in the spherical coordinate system constructed based on the predetermined three-dimensional space, and the second coordinate axis is the second rotation angle of the rotation axis,

Wherein, the first coordinate axis and the second coordinate axis are perpendicular to each other.
The device according to claim 12, wherein the size information of the object to be detected projected onto the predetermined two-dimensional plane includes the width of the object to be detected and the height of the object to be detected; the size information determiner Modules include:

an azimuth size determination unit, configured to determine first size information of the bounding box of each object to be detected according to the width of each object to be detected and the mapping relationship, where the first size information includes the bounding box of the object to be detected half the azimuthal dimension of the box in the spherical coordinate system constructed based on the predetermined three-dimensional space; and

a pitch size determination unit, configured to determine second size information of the bounding box of each object to be detected according to the height of each object to be detected and the mapping relationship, where the second size information includes the bounding box of the object to be detected Half of the pitch size of the box in the spherical coordinate system constructed based on the predetermined three-dimensional space.
The apparatus according to claim 13, wherein the collision result determination module comprises:

The first difference determination submodule is used to determine the first difference between the two first rotation angles of the two objects to be detected, and to determine the difference between the two second rotation angles of the two objects to be detected. the second difference between;

A first size sum determination sub-module is used to determine the sum of the first size information of the two bounding boxes of the two objects to be detected, and obtain the first size sum; and is used to determine the two of the two objects to be detected. summing the second size information of the bounding box to obtain a second size sum; and

The first collision determination sub-module is configured to determine two collisions based on the size relationship between the first difference value and the first size sum and the size relationship between the second difference value and the second size sum. collision result of the object to be detected.
The apparatus according to claim 13, wherein the size information determination submodule further comprises:

A size information determination unit, configured to determine the larger value of the first size information and the second size information as size information of the bounding box of each of the objects to be detected.
The apparatus of claim 15, wherein the collision result determination module comprises:

The second difference determination submodule is used to determine the first difference between the two first rotation angles of the two objects to be detected, and to determine the two second rotation angles of the two objects to be detected the second difference between;

a second size sum determination submodule, configured to determine the sum of the size information of the two bounding boxes of the two objects to be detected, and obtain the size sum; and

A second collision determination submodule, configured to determine a collision result of the two objects to be detected based on the magnitude relationship between the arithmetic square root of the first difference and the second difference and the sum of the sizes.
An electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any one of claims 1 to 8 Methods.
A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.
A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-8.